Muutke küpsiste eelistusi

E-raamat: Artificial Organic Networks: Artificial Intelligence Based on Carbon Networks

, ,
Teised raamatud teemal:
  • Formaat - PDF+DRM
  • Hind: 110,53 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Lisa ostukorvi
  • Lisa soovinimekirja
  • See e-raamat on mõeldud ainult isiklikuks kasutamiseks. E-raamatuid ei saa tagastada.
Artificial Organic Networks: Artificial Intelligence Based on Carbon NetworksSuurem pilt
Teised raamatud teemal:

DRM piirangud

  • Kopeerimine (copy/paste):

    ei ole lubatud

  • Printimine:

    ei ole lubatud

  • Kasutamine:

    Digitaalõiguste kaitse (DRM)
    Kirjastus on väljastanud selle e-raamatu krüpteeritud kujul, mis tähendab, et selle lugemiseks peate installeerima spetsiaalse tarkvara. Samuti peate looma endale  Adobe ID Rohkem infot siin. E-raamatut saab lugeda 1 kasutaja ning alla laadida kuni 6'de seadmesse (kõik autoriseeritud sama Adobe ID-ga).

    Vajalik tarkvara
    Mobiilsetes seadmetes (telefon või tahvelarvuti) lugemiseks peate installeerima selle tasuta rakenduse: PocketBook Reader (iOS / Android)

    PC või Mac seadmes lugemiseks peate installima Adobe Digital Editionsi (Seeon tasuta rakendus spetsiaalselt e-raamatute lugemiseks. Seda ei tohi segamini ajada Adober Reader'iga, mis tõenäoliselt on juba teie arvutisse installeeritud )

    Seda e-raamatut ei saa lugeda Amazon Kindle's. 

This monograph describes the synthesis and use of biologically-inspired artificial hydrocarbon networks (AHNs) for approximation models associated with machine learning and a novel computational algorithm with which to exploit them. The reader is first introduced to various kinds of algorithms designed to deal with approximation problems and then, via some conventional ideas of organic chemistry, to the creation and characterization of artificial organic networks and AHNs in particular.

The advantages of using organic networks are discussed with the rules to be followed to adapt the network to its objectives. Graph theory is used as the basis of the necessary formalism. Simulated and experimental examples of the use of fuzzy logic and genetic algorithms with organic neural networks are presented and a number of modeling problems suitable for treatment by AHNs are described:

·        approximation;

·        inference;

·        clustering;

·        control;

·        classification; and

·        audio-signal filtering.

The text finishes with a consideration of directions in which AHNs could be implemented and developed in future. A complete LabVIEW toolkit, downloadable from the books page at springer.com enables readers to design and implement organic neural networks of their own.

The novel approach to creating networks suitable for machine learning systems demonstrated in Artificial Organic Networks will be of interest to academic researchers and graduate students working in areas associated with computational intelligence, intelligent control, systems approximation and complex networks.
1 Introduction to Modeling Problems
1(30)
1.1 The Modeling Problem
2(1)
1.2 Review of Machine Learning
3(4)
1.2.1 Learning Algorithms
4(2)
1.2.2 Classification Algorithms
6(1)
1.3 Nature-Inspired Computing
7(10)
1.3.1 Metaheuristic Algorithms
8(1)
1.3.2 Evolutionary Algorithms
9(1)
1.3.3 Biologically Inspired Algorithms
9(5)
1.3.4 Chemically Inspired Algorithms
14(3)
1.4 Comparison of Algorithms for Modeling Problems
17(7)
1.4.1 Complexity and Stability in Modeling Problems
17(3)
1.4.2 Artificial Organic Networks and Modeling Problems
20(4)
1.5 Motivation of Artificial Organic Networks
24(7)
References
29(2)
2 Chemical Organic Compounds
31(22)
2.1 The Importance of Organic Chemistry
32(1)
2.2 Basic Concepts of Organic Compounds
33(7)
2.2.1 Structural Definitions
34(2)
2.2.2 Chemical Definitions
36(4)
2.3 Covalent Bonding
40(2)
2.3.1 Characterization of Covalent Bonds
40(2)
2.4 Energy in Organic Compounds
42(3)
2.4.1 Energy Level Scheme
42(1)
2.4.2 Measures of Energy
43(2)
2.5 Classification of Organic Compounds
45(4)
2.5.1 Hydrocarbons
45(1)
2.5.2 Alcohols, Ethers, and Thiols
46(1)
2.5.3 Amines
47(1)
2.5.4 Aldehydes, Ketones, and Carboxylic Acids
47(1)
2.5.5 Polymers
48(1)
2.5.6 Carbohydrates, Lipids, Amino Acids, and Proteins
48(1)
2.5.7 Nucleic Acids
49(1)
2.6 Organic Compounds as Inspiration
49(4)
2.6.1 Motivation
49(1)
2.6.2 Characteristics
50(2)
References
52(1)
3 Artificial Organic Networks
53(20)
3.1 Overview of Artificial Organic Networks
53(3)
3.1.1 The Metaphor
54(1)
3.1.2 Objectives
55(1)
3.2 Artificial Organic Compounds
56(10)
3.2.1 Components
56(7)
3.2.2 Interactions
63(3)
3.3 Networks of Artificial Organic Compounds
66(1)
3.3.1 The Structure
66(1)
3.3.2 The Behavior
66(1)
3.3.3 Mixtures of Compounds
66(1)
3.4 The Technique of Artificial Organic Networks
67(3)
3.4.1 Levels of Energy in Components
67(1)
3.4.2 Formal Definition of Artificial Organic Networks
68(1)
3.4.3 Model of Artificial Organic Networks
69(1)
3.5 Implementation Issues
70(3)
3.5.1 The Search Topological Parameters Problem
70(1)
3.5.2 The Build Topological Structure Problem
71(1)
3.5.3 Artificial Organic Networks-Based Algorithms
72(1)
References
72(1)
4 Artificial Hydrocarbon Networks
73(40)
4.1 Introduction to Artificial Hydrocarbon Networks
73(2)
4.1.1 Chemical Inspiration
73(1)
4.1.2 Objectives and Scope
74(1)
4.2 Basics of Artificial Hydrocarbon Networks
75(27)
4.2.1 Components
75(6)
4.2.2 Interactions
81(4)
4.2.3 The Algorithm
85(16)
4.2.4 Mathematical Formulation
101(1)
4.3 Metrics of Artificial Hydrocarbon Networks
102(6)
4.3.1 Computational Complexity
102(3)
4.3.2 Stability
105(3)
4.4 Artificial Hydrocarbon Networks Practical Features
108(5)
4.4.1 Partial Knowledge Representation
108(2)
4.4.2 Practical Issues in Partial Knowledge Extraction
110(1)
References
111(2)
5 Enhancements of Artificial Hydrocarbon Networks
113(18)
5.1 Optimization of the Number of Molecules
113(6)
5.1.1 The Hess' Law
113(1)
5.1.2 Boiling and Melting Points in Hydrocarbons
114(1)
5.1.3 Enthalpy in Artificial Hydrocarbon Networks
115(4)
5.2 Extension to the Multidimensional Case
119(8)
5.2.1 Components and Interactions
120(4)
5.2.2 Multidimensional AHN-Algorithm
124(3)
5.3 Recursive Networks Using Aromatic Compounds
127(4)
References
129(2)
6 Notes on Modeling Problems Using Artificial Hydrocarbon Networks
131(24)
6.1 Approximation Problems
131(11)
6.1.1 Approximation of Univariate Functions
132(5)
6.1.2 Approximation of Multivariate Functions
137(5)
6.2 Clustering Problems
142(7)
6.2.1 Linear Classifiers
142(3)
6.2.2 Nonlinear Classifiers
145(4)
6.3 Guidelines for Real-World Applications
149(6)
6.3.1 Inheritance of Information
150(2)
6.3.2 Catalog Based on Artificial Compounds
152(1)
6.3.3 Using Metadata
152(1)
References
153(2)
7 Applications of Artificial Hydrocarbon Networks
155(36)
7.1 Filtering Process in Audio Signals
155(10)
7.1.1 Background and Problem Statement
156(1)
7.1.2 Methodology
157(2)
7.1.3 Results and Discussion
159(6)
7.2 Position Control of DC Motor Using AHN-Fuzzy Inference Systems
165(18)
7.2.1 Background and Problem Statement
166(6)
7.2.2 Methodology
172(5)
7.2.3 Results and Discussion
177(6)
7.3 Facial Recognition Based on Signal Identification Using AHNs
183(8)
7.3.1 Background and Problem Statement
183(2)
7.3.2 Methodology
185(2)
7.3.3 Results and Discussion
187(2)
References
189(2)
Appendix A Brief Review of Graph Theory 191(4)
Appendix B Experiment of Signal-Molecule Correlation 195(6)
Appendix C Practical Implementation of Artificial Hydrocarbon Networks 201(10)
Appendix D Artificial Organic Networks Toolkit Using LabVIEW™ 211(10)
Appendix E Examples of Artificial Hydrocarbon Networks in LabVIEW™ 221
Professor Dr. Arturo Molina is Rector of Mexico City Metropolitan Area of Tecnologico de Monterrey. Former General Director of Campus Ciudad de Mexico, Vice president of Research and Technological Development, and Dean of the School of Engineering and Architecture of  Campus Monterrey. He was  a visiting professor at UC Berkeley at Mechanical Engineering Department during his Sabbatical year. He received his PhD degree in Manufacturing Engineering at Loughborough University of Technology, England in July 1995, his University Doctor degree in Mechanical Engineering at the Technical University of Budapest, Hungary in November 1992, his M.Sc. degree and BSc. in Computer Science from Tecnologico de Monterrey, Campus Monterrey. Professor Molina is member of the National Researchers System of Mexico (SNI-Nivel II), Mexican Academy of Sciences, Member of the IFAC Council, and member of IFIP WG5.12 Working Group on Enterprise Integration Architectures and IFIP WG 5.3 Cooperation of Virtual Enterprises and Virtual Organizations. He has offered seminars and conferences in USA, Canada, Latin America and Europe and is in the Editorial Board of the International Journal of Computer Integrated Manufacturing, Annual Reviews in Control and International Journal of Networking and Virtual Organisations. He has worked as a consultant for important Mexican corporations, World Bank, Inter-American Development Bank (IADB) and United Nations Information and Communication Technologies (ICT) Task Force. He has been Latin American coordinator of important international projects related to the development of Information Technologies such as: COSME-GVE (Cooperation of Small and Medium Enterprises - Global Virtual Enterprise), ENAPS (European Network for Advanced Performance Studies), e-HUBS (e-Engineering enabled by Holonomic and Universal Broker services) and Global e-Engineering (Global Collaborative Engineering Environment for Integrated Product Development using Internet 2). Healso participated in the European Project (ECOLEAD European Collaborative networked Organizations LEADership initiative) funded by the 6th Framework of the European Commission, and coordinated the project PYME CREATIVA (Acronym in Spanish for CREAtion of Information Technologies for Value Added Networks) sponsored by the IADB and IBM Sur Grant. Nowadays he is the principal researcher of a 7th Framework of the European Commission related to Sustainable Mass Customization Mass Customization for Sustainability, and principal consultant of a technology transfer project to Peru of PyME CREATIVA sponsored by IADB.

Dr. Hiram Ponce-Espinosa is the author of the novel artificial intelligence technique called Artificial Organic Networks and author of the supervised learning algorithm so-called Artificial Hydrocarbon Networks.

 

He graduated from Tecnológico de Monterrey CCM, Mexico with a B.S. in Mechatronics Engineering (2008) and a Specialty in Control and Automation (2009). He also received both his Masters Degree in Engineering Science with specialization in Intelligent Control (2010) and his Ph.D. in Computer Sciences with specialization in Artificial Intelligence (2013) from the same Institute.

 

He has published several research articles for both international conferences and journals, two books in the field of artificial intelligence and robotics, and he has participated in a chapter book at LabVIEW: A Developers Guide to Real-World Integration (2012). He is also co-author of six patents, including the recognizedthird-party software Intelligent Control Toolkit for LabVIEW (ICTL).

 

He is currently co-founder and CEO at Solarium Labs, the first Mexican research center 100% dedicated to develop intelligent systems for academy and industry. He is also professor and researcher at Tecnológico de Monterrey CCM, Mexico. His main interests are: artificial intelligence, engineering control systems, machine learning, and education.
Lisainfo e-raamatute kohta Lisainfo e-raamatute kohta
Püsilink: https://www.kriso.ee/db/97833190247212e.html
Märksõnad: